# Effective Face Frontalization in Unconstrained Images

arXiv: https://arxiv.org/abs/1411.7964 · HTML: https://mlsanity.com/paper/1411.7964/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2014.

## Built on by (most cited first, 30 of 34)

- [Realistic One-shot Mesh-based Head Avatars](https://mlsanity.com/paper/2206.08343/) (2022)
- [3D face reconstruction with dense landmarks](https://mlsanity.com/paper/2204.02776/) (2022)
- [Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers](https://mlsanity.com/paper/2108.02922/) (2021)
- [Joint Face Image Restoration and Frontalization for Recognition](https://mlsanity.com/paper/2105.09907/) (2021)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [Egocentric Videoconferencing](https://mlsanity.com/paper/2107.03109/) (2021)
- [3D Face Reconstruction: the Road to Forensics](https://mlsanity.com/paper/2309.11357/) (2023)
- [Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks](https://mlsanity.com/paper/2111.07047/) (2021)
- [DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs](https://mlsanity.com/paper/2302.12253/) (2023)
- [Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape](https://mlsanity.com/paper/2204.04379/) (2022)
- [Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection](https://mlsanity.com/paper/2411.07167/) (2024)
- [Expression-preserving face frontalization improves visually assisted speech processing](https://mlsanity.com/paper/2204.02810/) (2022)
- [3D Face Reconstruction for Forensic Recognition -- A Survey](https://mlsanity.com/paper/2303.11164/) (2023)
- [Exploiting Multiple Representations: 3D Face Biometrics Fusion with Application to Surveillance](https://mlsanity.com/paper/2504.18886/) (2025)
- [Weakly-Supervised Photo-realistic Texture Generation for 3D Face Reconstruction](https://mlsanity.com/paper/2106.08148/) (2021)
- [PAM: Pose Attention Module for Pose-Invariant Face Recognition](https://mlsanity.com/paper/2111.11940/) (2021)
- [Pose Attention-Guided Profile-to-Frontal Face Recognition](https://mlsanity.com/paper/2209.07001/) (2022)
- [A Study on the Impact of Face Image Quality on Face Recognition in the Wild](https://mlsanity.com/paper/2307.02679/) (2023)
- [2D Image head pose estimation via latent space regression under occlusion settings](https://mlsanity.com/paper/2311.06038/) (2023)
- [Exploring 3D Face Reconstruction and Fusion Methods for Face Verification: A Case-Study in Video Surveillance](https://mlsanity.com/paper/2409.10481/) (2024)
- [FaceRefiner: High-Fidelity Facial Texture Refinement with Differentiable Rendering-based Style Transfer](https://mlsanity.com/paper/2601.04520/) (2026)
- [An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking](https://mlsanity.com/paper/2103.07615/) (2021)
- [Fiducial Focus Augmentation for Facial Landmark Detection](https://mlsanity.com/paper/2402.15044/) (2024)
- [Learning to Deblur and Rotate Motion-Blurred Faces](https://mlsanity.com/paper/2112.07599/) (2021)
- [2D-3D Attention and Entropy for Pose Robust 2D Facial Recognition](https://mlsanity.com/paper/2505.09073/) (2025)
- [Active Face Frontalization using Commodity Unmanned Aerial Vehicles](https://mlsanity.com/paper/2102.08542/) (2021)
- [Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space](https://mlsanity.com/paper/2108.10265/) (2021)
- [Generating Animatable 3D Cartoon Faces from Single Portraits](https://mlsanity.com/paper/2307.01468/) (2023)
- [Facial Landmark Detection Evaluation on MOBIO Database](https://mlsanity.com/paper/2307.03329/) (2023)
- [Face Image Quality Enhancement Study for Face Recognition](https://mlsanity.com/paper/2307.05534/) (2023)

## Abstract (arXiv)

"Frontalization" is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos. Recent reports have suggested that this process may substantially boost the performance of face recognition systems. This, by transforming the challenging problem of recognizing faces viewed from unconstrained viewpoints to the easier problem of recognizing faces in constrained, forward facing poses. Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image. We observe that 3D face shape estimation from unconstrained photos may be a harder problem than frontalization and can potentially introduce facial misalignments. Instead, we explore the simpler approach of using a single, unmodified, 3D surface as an approximation to the shape of all input faces. We show that this leads to a straightforward, efficient and easy to implement method for frontalization. More importantly, it produces aesthetic new frontal views and is surprisingly effective when used for face recognition and gender estimation.